Thanks to visit codestin.com
Credit goes to github.com

Skip to content

BUG, SIMD: Fix detecting NEON/ASIMD on aarch64 #21749

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 14, 2022

Conversation

seiko2plus
Copy link
Member

@seiko2plus seiko2plus commented Jun 14, 2022

closes #21747

TODO:

  • checking arm64 builds

@seiko2plus seiko2plus added the 09 - Backport-Candidate PRs tagged should be backported label Jun 14, 2022
@mattip mattip merged commit c3f0f99 into numpy:main Jun 14, 2022
@mattip
Copy link
Member

mattip commented Jun 14, 2022

Thanks @seiko2plus

@charris charris removed the 09 - Backport-Candidate PRs tagged should be backported label Jun 14, 2022
@dhomeier
Copy link
Contributor

Thanks for the quick fix! I've now run the benchmark suite before and after, and in general it seems to show a 10-30% speedup in many tests. Default settings for my M1 Max are now reported as

NumPy CPU features: NEON NEON_FP16 NEON_VFPV4 ASIMD ASIMDHP* ASIMDDP* ASIMDFHM?

@rgommers rgommers added the component: SIMD Issues in SIMD (fast instruction sets) code or machinery label Jul 12, 2022
@EwoutH
Copy link
Contributor

EwoutH commented Aug 30, 2022

@seiko2plus do you by any chance want to take a look at detecting SVE2 on Aarch64?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
00 - Bug component: SIMD Issues in SIMD (fast instruction sets) code or machinery
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Neon detection on M1 needs fixing for 1.23.0 release
6 participants